Nikolaos Tsagkas

prof_pic_2_25.jpg

Currently, I am a research intern at the Samsung Research Artificial Intelligence Center in Cambridge, UK.

I am a PhD candidate at the School of Informatics, University of Edinburgh, supported by the Edinburgh Centre for Robotics. I am fortunate to be advised by Prof. Chris Xiaoxuan Lu (UCL) and Prof. Oisin Mac Aodha (UoE). My research focuses on leveraging pre-trained visual representations for robot learning.

Prior to my PhD, I earned an MSc in Artificial Intelligence with distinction in 2021 at the University of Edinburgh, under the supervision of Prof. Chris Williams, where I worked on inference and learning for generative capsule models. Before that, I spent a year as a Data Scientist at Ernst & Young. I hold a BSc and MSc in Electrical & Computer Engineering (2019) from the University of Patras, Greece, where I researched real-time hand-gesture recognition using sEMG signals under the guidance of Prof. A. Skodras.

📢 Latest News:
View older news

Publications

  1. afa_thumbnail_smaller.gif
    Attentive Feature Aggregation, Or: How Policies Learn to Stop Worrying about Robustness and Attend to Task-Relevant Visual Cues
    Nikolaos Tsagkas , Andreas Sochopoulos , Duolikun Danier , Sethu Vijayakumar , Alexandros Kouris , Chris Xiaoxuan Lu , and Oisin Mac Aodha
    In ArXiv Preprint , 2025
    arXiv HTML Code
  2. temporal_thumbnail.gif
    The Temporal Trap: Entanglement in Pre-Trained Visual Representations for Visuomotor Policy Learning
    Nikolaos Tsagkas , Andreas Sochopoulos , Duolikun Danier , Chris Xiaoxuan Lu , and Oisin Mac Aodha
    In ArXiv Preprint , 2025
    arXiv Code
  3. zipper_16fps_240.gif
    Fast Flow-based Visuomotor Policies via Conditional Optimal Transport Couplings
    Andreas Sochopoulos , Nikolay Malkin , Nikolaos Tsagkas , João Moura , Michael Gienger , and Sethu Vijayakumar
    In Conference on Robot Learning (CoRL), Seoul, South Korea , 2025
    arXiv HTML Code
  4. pvrobo_thumbnail_distractors_short.gif
    When Pre-trained Visual Representations Fall Short: Limitations in Visuo-Motor Robot Learning [Spotlight Talk + Poster]
    Nikolaos Tsagkas , Andreas Sochopoulos , Duolikun Danier , Sethu Vijayakumar , Chris Xiaoxuan Lu , and Oisin Mac Aodha
    In EAI@Computer Vision and Pattern Recognition (CVPR) , 2025
    HTML Code
  5. affordance_thumbnail_150.gif
    Learning Precise Affordances from Egocentric Videos for Robotic Manipulation
    Gen Li , Nikolaos Tsagkas , Jifei Song , Ruaridh Mon-Williams , Sethu Vijayakumar , Kun Shao , and Laura Sevilla-Lara
    In IEEE/CVF International Conference on Computer Vision (ICCV), Hawaii, USA , 2025
    arXiv HTML
  6. c2g_thumbnail_150.gif
    Click to Grasp: Zero-Shot Precise Manipulation via Visual Diffusion Descriptors [Oral Pitch + Poster]
    Nikolaos Tsagkas , Jack Rome , Subramanian Ramamoorthy , Oisin Mac Aodha , and Chris Xiaoxuan Lu
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Abu Dhabi, UAE , 2024
    arXiv HTML Code
  7. vl-fields_thumbnail.gif
    VL-Fields: Towards Language-Grounded Neural Implicit Spatial Representations [Spotlight Talk + Poster]
    Nikolaos Tsagkas , Oisin Mac Aodha , and Chris Xiaoxuan Lu
    In International Conference on Robotics and Automation (ICRA) Workshops, London, UK , 2023
    arXiv HTML
  8. ecgm_thumbnail.gif
    Inference and Learning for Generative Capsule Models
    Alfredo Nazabal* , Nikolaos Tsagkas* , and Christopher K. I. Williams
    Neural Computation, 2023
    arXiv Code
  9. semg_thumbnail.gif
    On the Use of Deeper CNNs in Hand Gesture Recognition Based on sEMG Signals [Oral Presentation]
    Nikolaos Tsagkas , Panagiotis Tsinganos , and Athanassios Skodras
    In 10th International Conference on Information, Intelligence, Systems and Applications (IISA), Patras, Greece , 2019
    PDF Code